Yuxi
可私有部署的多租户知识智能体平台：统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
Runssource: GitHubhomepagePythonMITcommit bd07ab4ac4fa
Python, MIT licensed. The project labels itself: agentic rag, ai agents, deepagents, docker, document ai, fastapi, harness and kbqa.
Yuxi runs. An Argusic agent installed it in 9.7 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Backend Python dependencies installed and locked; all 1640 backend unit tests pass; all 164 web unit tests pass; Vite production build completes successfully; engineering trust contracts and lint checks pass. Two minor test permission-assertion bugs fixed (umask compatibility) and one Node.js version gap resolved (rolldown native binding via explicit dep + Node 20 for test/build).
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 97.3 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Node.js 18.19.1 (system) missing styleText export from node:util; rolldown native binding not resolved3 minutes
- test_kubernetes_storage_init_migrates_only_real_entries: umask 0002 causes 0775 vs expected 0755 on tmp_path directory1.5 minutes
- test_runtime_identity_migration_preserves_symlink_without_following_target: same umask 0002 issue1.5 minutes
- Install time
- 10 minutes
- Cold machine to finish
- 25 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- pytest backend unit tests: 1640 passed, 7 warnings; web unit tests: 164 passed, 0 failed; vite build: built 8442 modules in 5.92s; engineering contracts: passed; ruff lint: all checks passed
- Model tokens used
- 209,240
- Exact commit tested
- bd07ab4ac4fa
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
## Final verification | Check | Result | |---|---| | `uv sync` (Python deps install) | succeeded | | `uv run pytest test/unit -m "not slow"` | **1640 passed**, 7 warnings, 0 failures | | `ruff check package` | All checks passed | | `verify_engineering_contracts.py` | 工程信任检查通过 (56 decisions / 5 workflows / 4 agents) | | `scripts.test_verify_engineering_contracts` | 61 tests OK | | `pnpm install` (web deps) | succeeded | | `node --test test/unit/` (with Node 20) | **164 passed**, 0 failures | | `vite build` (with Node 20) | **✓ built in 5.92s**, 8442 modules | | `git diff --check` | clean (4 files changed: 2 test fixes, 1 binding dep, 1 lockfile) |
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 9.7 minutes, faster than the median of the 3 comparable projects Argusic has measured.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 3 times, so the result is not a one-off.
Of the 4 agentic-rag projects Argusic has installed and timed, Yuxi was the 2nd fastest to reach a running state, and 2 of 4 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 9.7 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agentic-ragai-agentsdeepagentsdockerdocument-aifastapiharnesskbqakgqaknowledge-baseknowledge-graphlanggraphllmsmcpmilvusmulti-agentneo4jragself-hostedvue
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/yuxi)Questions
- Does Yuxi run?
- Yes. Yuxi runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test Yuxi?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit bd07ab4ac4fa. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test Yuxi?
- The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Yuxi take to install?
- 9.7 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does Yuxi need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Yuxi?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does Yuxi compare with the alternatives?
- Of the 4 agentic-rag projects Argusic has installed and timed, Yuxi was the 2nd fastest to reach a running state, and 2 of 4 reached one at all.
- Where is the evidence for Yuxi?
- All 3 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.